org.apache.tez.mapreduce.examples.WordCountMRRTest.java Source code

Introduction

Here is the source code for org.apache.tez.mapreduce.examples.WordCountMRRTest.java

Source

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.tez.mapreduce.examples;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.tez.mapreduce.hadoop.MRJobConfig;
import org.apache.tez.mapreduce.hadoop.MultiStageMRConfigUtil;

public class WordCountMRRTest {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntermediateReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {

            String keyString = key.toString();

            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            String[] splits = keyString.split("\\.");
            for (String split : splits) {
                context.write(new Text(split), result);
            }

        }
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();

        // TODO HACKS This needs to be fixed once the mrr api is detailed.
        // Has to be set before initialzing job, since it creates a copy.
        // Alternately use JonConf. 
        conf.setInt(MRJobConfig.MRR_INTERMEDIATE_STAGES, 1);
        conf.setClass(MultiStageMRConfigUtil.getPropertyNameForIntermediateStage(1, "mapreduce.job.combine.class"),
                IntermediateReducer.class, Reducer.class);
        conf.setClass(MultiStageMRConfigUtil.getPropertyNameForIntermediateStage(1, "mapreduce.job.reduce.class"),
                IntermediateReducer.class, Reducer.class);
        conf.set(MultiStageMRConfigUtil.getPropertyNameForIntermediateStage(1, "mapreduce.map.output.value.class"),
                IntWritable.class.getName());

        System.err.println("Running wordcountMrrTest");
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcountmrrtest <in> <out>");
            System.exit(2);
        }
        Job job = new Job(conf, "word count mrr");
        job.setJarByClass(WordCountMRRTest.class);
        job.setMapperClass(TokenizerMapper.class);

        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}